add tokenizer

vocab.json

@@ -1 +1 @@
-{"u": 0, "a": 1, "y": 2, "i": 3, "s": 4, "p": 5, "l": 6, "f": 7, "q": 8, "x": 9, "b": 10, "v": 11, "h": 12, "o": 13, "n": 14, "w": 15, "k": 16, "c": 18, "g": 19, "j": 20, "m": 21, "d": 22, "t": 23, "e": 24, "r": 25, "z": 26, "'": 27, "|": 17, "[UNK]": 28, "[PAD]": 29}
+{"s": 0, "t": 1, "g": 2, "v": 3, "r": 4, "e": 5, "w": 6, "a": 7, "k": 8, "f": 9, "c": 10, "z": 11, "p": 12, "m": 13, "j": 14, "q": 15, "h": 16, "o": 17, "n": 18, "y": 19, "x": 21, "u": 22, "i": 23, "b": 24, "l": 25, "d": 26, "'": 27, "|": 20, "[UNK]": 28, "[PAD]": 29}